Skill Gap Analysis

import pandas as pd
df = pd.read_parquet("data/eda.parquet")

---------------------------------------------------------------------------
ImportError                               Traceback (most recent call last)
Cell In[1], line 2
      1 import pandas as pd
----> 2 df = pd.read_parquet("data/eda.parquet")

File /opt/hostedtoolcache/Python/3.11.12/x64/lib/python3.11/site-packages/pandas/io/parquet.py:651, in read_parquet(path, engine, columns, storage_options, use_nullable_dtypes, dtype_backend, filesystem, filters, **kwargs)
    498 @doc(storage_options=_shared_docs["storage_options"])
    499 def read_parquet(
    500     path: FilePath | ReadBuffer[bytes],
   (...)
    508     **kwargs,
    509 ) -> DataFrame:
    510     """
    511     Load a parquet object from the file path, returning a DataFrame.
    512 
   (...)
    648     1    4    9
    649     """
--> 651     impl = get_engine(engine)
    653     if use_nullable_dtypes is not lib.no_default:
    654         msg = (
    655             "The argument 'use_nullable_dtypes' is deprecated and will be removed "
    656             "in a future version."
    657         )

File /opt/hostedtoolcache/Python/3.11.12/x64/lib/python3.11/site-packages/pandas/io/parquet.py:67, in get_engine(engine)
     64         except ImportError as err:
     65             error_msgs += "\n - " + str(err)
---> 67     raise ImportError(
     68         "Unable to find a usable engine; "
     69         "tried using: 'pyarrow', 'fastparquet'.\n"
     70         "A suitable version of "
     71         "pyarrow or fastparquet is required for parquet "
     72         "support.\n"
     73         "Trying to import the above resulted in these errors:"
     74         f"{error_msgs}"
     75     )
     77 if engine == "pyarrow":
     78     return PyArrowImpl()

ImportError: Unable to find a usable engine; tried using: 'pyarrow', 'fastparquet'.
A suitable version of pyarrow or fastparquet is required for parquet support.
Trying to import the above resulted in these errors:
 - Missing optional dependency 'pyarrow'. pyarrow is required for parquet support. Use pip or conda to install pyarrow.
 - Missing optional dependency 'fastparquet'. fastparquet is required for parquet support. Use pip or conda to install fastparquet.

Group 11 Skill

import pandas as pd

skills_data = {
    "Name": ["Binderiya", "Pranjul", "Pratham", "Panyang"],
    "Python": [4, 4, 5, 3],
    "SQL": [4, 4, 5, 4],
    "Machine Learning": [2, 3, 2, 2],
    "PySpark": [3, 3, 3, 3],
    "Excel": [4, 5, 5, 4],
    "Data Visualization": [5, 5, 3, 3],
    "Power Bi/ Tableau": [4, 5, 3, 4],
    "Version Control Git": [4, 4, 3, 3],
    "ETL/Data pipeline": [3, 2, 1, 2],
    "Communication": [4, 4, 5, 3],
    "Project Management": [5, 5, 5, 3],
    "Cloud Computing": [4, 4, 2, 2]
}

df_skills = pd.DataFrame(skills_data)
df_skills.set_index("Name", inplace=True)
df_skills

	Python	SQL	Machine Learning	PySpark	Excel	Data Visualization	Power Bi/ Tableau	Version Control Git	ETL/Data pipeline	Communication	Project Management	Cloud Computing
Name
Binderiya	4	4	2	3	4	5	4	4	3	4	5	4
Pranjul	4	4	3	3	5	5	5	4	2	4	5	4
Pratham	5	5	2	3	5	3	3	3	1	5	5	2
Panyang	3	4	2	3	4	3	4	3	2	3	3	2

import plotly.express as px

fig = px.imshow(
    df_skills,
    text_auto=True,                
    color_continuous_scale="YlGnBu",
    aspect="auto"                 
)

fig.update_layout(
    title="Team Skill Levels Heatmap",
    xaxis_title="Skills",
    yaxis_title="Team Members",
    width=700,
    height=400,
    margin=dict(l=50, r=20, t=50, b=50)
)

fig.write_html(
    "figures/skill_gap_plo1.html",
    include_plotlyjs="cdn",
    full_html=False
)

import plotly.graph_objects as go
from IPython.display import IFrame
fig = go.Figure()

for name in df_skills.index:
    values = df_skills.loc[name].tolist()
    values += values[:1]  # close the loop
    fig.add_trace(go.Scatterpolar(
        r=values,
        theta=df_skills.columns.tolist() + [df_skills.columns[0]],
        fill='toself',
        name=name
    ))

fig.update_layout(
    polar=dict(radialaxis=dict(visible=True, range=[0, 5])),
    showlegend=True,
    title='Team Skills Radar Chart'
)

fig.write_html(
    "figures/skill_gap_plo2.html",
    include_plotlyjs="cdn",
    full_html=False
)

Interactive Radar Chart

From this radar chart visualization we can see that our team has a lot of room for improvement for skills like PySpark and Machine Learning. Also we can see that not a lot of our team mates are confident in their skills in Cloud Computing and ETL.

Top Skills

keywords = ['Data Analyst', 'Business Analyst', 'Data Engineering', 'Deep Learning',
            'Data Science', 'Data Analysis','Data Analytics',  'Market Research Analyst' 
            'LLM', 'Language Model', 'NLP', 'Natural Language Processing',
            'Computer Vision', 'Business Intelligence Analyst', 'Quantitative Analyst', 'Operations Analyst']

match = lambda col: df[col].str.contains('|'.join(keywords), case=False, na=False)

df['DATA_ANALYST_JOB'] = match('TITLE_NAME') \
             | match('SKILLS_NAME') \
             | match('SPECIALIZED_SKILLS_NAME') 
df['DATA_ANALYST_JOB'].value_counts()

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[5], line 8
      1 keywords = ['Data Analyst', 'Business Analyst', 'Data Engineering', 'Deep Learning',
      2             'Data Science', 'Data Analysis','Data Analytics',  'Market Research Analyst' 
      3             'LLM', 'Language Model', 'NLP', 'Natural Language Processing',
      4             'Computer Vision', 'Business Intelligence Analyst', 'Quantitative Analyst', 'Operations Analyst']
      6 match = lambda col: df[col].str.contains('|'.join(keywords), case=False, na=False)
----> 8 df['DATA_ANALYST_JOB'] = match('TITLE_NAME') \
      9              | match('SKILLS_NAME') \
     10              | match('SPECIALIZED_SKILLS_NAME') 
     11 df['DATA_ANALYST_JOB'].value_counts()

Cell In[5], line 6, in <lambda>(col)
      1 keywords = ['Data Analyst', 'Business Analyst', 'Data Engineering', 'Deep Learning',
      2             'Data Science', 'Data Analysis','Data Analytics',  'Market Research Analyst' 
      3             'LLM', 'Language Model', 'NLP', 'Natural Language Processing',
      4             'Computer Vision', 'Business Intelligence Analyst', 'Quantitative Analyst', 'Operations Analyst']
----> 6 match = lambda col: df[col].str.contains('|'.join(keywords), case=False, na=False)
      8 df['DATA_ANALYST_JOB'] = match('TITLE_NAME') \
      9              | match('SKILLS_NAME') \
     10              | match('SPECIALIZED_SKILLS_NAME') 
     11 df['DATA_ANALYST_JOB'].value_counts()

NameError: name 'df' is not defined

import ast
import pandas as pd
import matplotlib.pyplot as plt
import plotly.express as px

# Safely apply literal_eval only to non-null values
df['SKILLS'] = df['SKILLS_NAME'].apply(lambda x: ast.literal_eval(x) if pd.notnull(x) else [])


data_skills = df[df['DATA_ANALYST_JOB']]['SKILLS'].explode().value_counts().reset_index()
data_skills.columns = ['Skill', 'Count']

fig = px.bar(data_skills, x='Skill', y='Count',
             title="Top Skills",
             labels={'Skill': 'Skill Name', 'Count': 'Frequency'},
             color='Skill')
df_skills.index = df_skills.index.str.strip()

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[6], line 7
      4 import plotly.express as px
      6 # Safely apply literal_eval only to non-null values
----> 7 df['SKILLS'] = df['SKILLS_NAME'].apply(lambda x: ast.literal_eval(x) if pd.notnull(x) else [])
     10 data_skills = df[df['DATA_ANALYST_JOB']]['SKILLS'].explode().value_counts().reset_index()
     11 data_skills.columns = ['Skill', 'Count']

NameError: name 'df' is not defined

from collections import defaultdict

# Lowercase everything
team_skills = [s.lower().strip() for s in df_skills.columns]
job_demand_raw = data_skills.copy()
job_demand_raw['Skill'] = job_demand_raw['Skill'].str.lower().str.strip()

# New dict to map cleaned team skill to total count from job postings
skill_demand_map = defaultdict(int)

for _, row in job_demand_raw.iterrows():
    skill_in_posting = row['Skill']
    count = row['Count']
    for team_skill in team_skills:
        if team_skill in skill_in_posting:
            skill_demand_map[team_skill] += count

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[7], line 5
      3 # Lowercase everything
      4 team_skills = [s.lower().strip() for s in df_skills.columns]
----> 5 job_demand_raw = data_skills.copy()
      6 job_demand_raw['Skill'] = job_demand_raw['Skill'].str.lower().str.strip()
      8 # New dict to map cleaned team skill to total count from job postings

NameError: name 'data_skills' is not defined

team_skills = [s.strip().lower() for s in df_skills.columns]
print("Team skills:", team_skills)
print(job_demand_raw['Skill'].head(10).tolist())
for skill_text in job_demand_raw['Skill'].head(10):
    for team_skill in team_skills:
        if team_skill in skill_text:
            print(f" '{team_skill}' found in: '{skill_text}'")

Team skills: ['python', 'sql', 'machine learning', 'pyspark', 'excel', 'data visualization', 'power bi/ tableau', 'version control git', 'etl/data pipeline', 'communication', 'project management', 'cloud computing']

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[8], line 3
      1 team_skills = [s.strip().lower() for s in df_skills.columns]
      2 print("Team skills:", team_skills)
----> 3 print(job_demand_raw['Skill'].head(10).tolist())
      4 for skill_text in job_demand_raw['Skill'].head(10):
      5     for team_skill in team_skills:

NameError: name 'job_demand_raw' is not defined

for _, row in job_demand_raw.iterrows():
    skill_text = row['Skill']
    count = row['Count']
    for team_skill in team_skills:
        if team_skill in skill_text:  # no regex, just substring
            skill_demand_map[team_skill] += count

job_demand = pd.Series(skill_demand_map)
print(job_demand)

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[9], line 1
----> 1 for _, row in job_demand_raw.iterrows():
      2     skill_text = row['Skill']
      3     count = row['Count']

NameError: name 'job_demand_raw' is not defined

job_demand = pd.Series(skill_demand_map)
job_demand.name = "Count"
team_avg = df_skills.mean()
team_avg.index = team_avg.index.str.strip().str.lower() 
# Now match only overlapping skills
common_skills = job_demand.index.intersection(team_avg.index)
team_avg = team_avg[common_skills]
job_demand = job_demand[common_skills]

# Normalize job demand
job_demand_normalized = 5 * (job_demand / job_demand.max())
job_demand_normalized.name = "Job Demand (Normalized)"

# Combine
comparison_df = pd.concat([team_avg, job_demand_normalized], axis=1)
comparison_df.columns = ["Team Average Skill", "Job Demand (Normalized)"]
comparison_df["Skill Gap"] = comparison_df["Job Demand (Normalized)"] - comparison_df["Team Average Skill"]
comparison_df.sort_values("Skill Gap", ascending=False, inplace=True)

comparison_df

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[10], line 1
----> 1 job_demand = pd.Series(skill_demand_map)
      2 job_demand.name = "Count"
      3 team_avg = df_skills.mean()

NameError: name 'skill_demand_map' is not defined

comparison_df = comparison_df.reset_index().rename(columns={"index": "Skill"})

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[11], line 1
----> 1 comparison_df = comparison_df.reset_index().rename(columns={"index": "Skill"})

NameError: name 'comparison_df' is not defined

import plotly.express as px

fig = px.bar(
    comparison_df,
    x='Skill',
    y='Skill Gap',
    color='Skill Gap',
    color_continuous_scale='RdBu_r',
    title='Skill Gaps: Job Market Expectations vs. Team Capability',
    labels={'Skill Gap': 'Gap (Job Demand - Team Skill)', 'Skill': 'Skill'},
)

fig.add_hline(y=0, line_dash='dash')
fig.update_layout(
    xaxis_tickangle=-45,
    yaxis_title='Gap (Positive = Market expects more)',
    font=dict(size=13),
    height=500,
    plot_bgcolor='white',
)
fig.write_html(
    "figures/skill_gap_plo3.html",
    include_plotlyjs="cdn",
    full_html=False
)

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[12], line 4
      1 import plotly.express as px
      3 fig = px.bar(
----> 4     comparison_df,
      5     x='Skill',
      6     y='Skill Gap',
      7     color='Skill Gap',
      8     color_continuous_scale='RdBu_r',
      9     title='Skill Gaps: Job Market Expectations vs. Team Capability',
     10     labels={'Skill Gap': 'Gap (Job Demand - Team Skill)', 'Skill': 'Skill'},
     11 )
     13 fig.add_hline(y=0, line_dash='dash')
     14 fig.update_layout(
     15     xaxis_tickangle=-45,
     16     yaxis_title='Gap (Positive = Market expects more)',
   (...)
     19     plot_bgcolor='white',
     20 )

NameError: name 'comparison_df' is not defined

This bar chart compares our team’s average proficiency in key data-related skills against job market expectations. Skills with positive values (like communication and SQL) indicate areas where market demand exceeds our current capabilities. On the other hand, negative values highlight areas where the team is ahead or closely aligned with market needs. Notably, skills like Python, cloud computing, and project management show the largest gaps, suggesting priority areas for upskilling.